Difference between revisions of "Speech-to-speech Translation"

From HLT@INESC-ID

(Related publications)
Line 34: Line 34:
  
 
* João de Almeida Varelas Graça, Diamantino António Caseiro, Luísa Coheur, [http://www.mt-archive.info/IWSLT-2007-Graca.pdf The INESC-ID IWSLT07 SMT System], In Proceedings of IWSLT International Workshop on Spoken Language Translation, pages 125-130, October 2007 ([http://iwslt07.itc.it/menu/presentations/sysSession4/INESC-ID.pdf slides pdf])
 
* João de Almeida Varelas Graça, Diamantino António Caseiro, Luísa Coheur, [http://www.mt-archive.info/IWSLT-2007-Graca.pdf The INESC-ID IWSLT07 SMT System], In Proceedings of IWSLT International Workshop on Spoken Language Translation, pages 125-130, October 2007 ([http://iwslt07.itc.it/menu/presentations/sysSession4/INESC-ID.pdf slides pdf])
 
* Mark Dredze, John Blitzer, Pratha Pratim Talukdar, Kuzman Ganchev, João de Almeida Varelas Graça, Fernando Pereira, [http://www.inesc-id.pt/pt/indicadores/Ficheiros/3988.pdf Frustratingly Hard Domain Adaptation for Parsing], In Conference on Computational Natural Language Learning, Association for Computational Linguistics, June 2007
 

Revision as of 17:54, 25 June 2008

People

Speech-to-speech machine translation is one of the most strategically relevant areas for L2F. The state of the art in speech translation is crucially dependent on the state of the art of several core technologies: speech recognition, machine translation and, to a lesser extent, text-to-speech synthesis (namely in what concerns voice morphing, in order to reproduce the source speakers’ characteristics in the target speaker’s voice). The main limitations of current machine translation systems are the lack of semantic interpretation and world knowledge as well as insufficient coverage of the large proportion of idiosyncratic linguistic phenomena in lexicon and syntax. The most promising approaches combine improved statistical methods with the improved knowledge-driven methods in a variety of clever ways.

L2F has been investing in statistically based speech-to-speech machine translation approaches based on weighted finite state transducers [Picó 2005] [Caseiro 2006], aiming at a tight integration between recognition and translation. WFSTs are especially well suited for combining different type of approaches, whether statistical or knowledge-based. The combination may be advantageous for achieving two different goals (i) include morpho-syntactic linguistic knowledge into the statistical machine translation paradigm and (ii) tackle the data sparseness problem for speech translation.

This research is carried out within the scope of a national project on “Weighted Finite State Transducers Applied to Spoken Language Processing”. Two PhD theses have recently started in this area.

Related resources

On-going projects

Related publications

  • João de Almeida Varelas Graça, Diamantino António Caseiro, Luísa Coheur, The INESC-ID IWSLT07 SMT System, In Proceedings of IWSLT International Workshop on Spoken Language Translation, pages 125-130, October 2007 (slides pdf)